.png){kind=icon}
返回
Self-supervised sub-category exploration for Pseudo label generation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.autcon.2023.104862.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Image segmentation-based applications have been actively investigated. However, it is non-trivial to prepare polygon annotations. Previous studies suggested pseudo label generation methods based on weakly supervised learning to lessen the burden of annotation. Nevertheless, the quality of pseudo labels could not be ideal due to target object characteristics and insufficient data size in the construction domain, as identified in this study. This study proposes a fusion architecture, SESC-CAM, to address the challenge, building upon weakly and self -supervised learning methods. The proposed architecture was validated on the AIM dataset, and the generated pseudo labels recorded a mIoU score of 64.99% and 67.65% after the refinement by using a conditional random field, and outperformed its predecessors by 11.29% and 9.14%. The refined pseudo labels were used to train a segmentation model and recorded a 74% mIoU score in semantic segmentation results. The findings of this study provide insights for automated training data preparation.
Keyword:
Self -supervised learning
Weakly supervised learning
Semantic segmentation
Pseudo label generation
Training data preparation
Construction vehicle
期刊
IF:
11.5
论文数:
6.3K
被引数:
4.2W
机构
引用论文
Automated annotation for visual recognition of construction resources using synthetic images使用合成图像对建筑资源进行视觉识别的自动注释
PREAI
分享收藏分享收藏Learning pseudo labels for semi-and-weakly supervised semantic segmentation用于半监督和弱监督语义分割的学习伪标签.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Road damage detection using super-resolution and semi-supervised learning with generative adversarial network使用生成对抗网络的超分辨率和半监督学习的道路损坏检测
OAAI
OAAI分享收藏Learning Self-supervised Low-Rank Network for Single-Stage Weakly and Semi-supervised Semantic Segmentation学习自监督低秩网络的单阶段弱半监督语义分割
OAAI
OAAI分享收藏
查看更多内容